© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115878
    Prev
    Next
    INDEX
    Explanations

    Objective-C/Swift syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     完全
    -0.83
     Dünya
    -0.81
    은
    -0.77
    waitKey
    -0.75
    nze
    -0.70
     با
    -0.70
    中原
    -0.69
    унк
    -0.68
    ](
    -0.67
    影片
    -0.67
    POSITIVE LOGITS
    记得
    0.98
    けどね
    0.85
     Criticism
    0.85
    recrow
    0.84
     _,
    0.84
    dopodob
    0.83
    なんですよ
    0.82
    eld
    0.80
    壳
    0.79
     remarks
    0.76
    Activations Density 0.006%

    No Known Activations